© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27592
    Prev
    Next
    INDEX
    Explanations

    coverage and services

    np_acts-logits-general · gemini-2.5-flash-lite

    Avoid, Adding weight, studies, difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ע
    0.53
    ב
    0.49
    Plan
    0.48
    Leon
    0.47
    Besch
    0.47
    бед
    0.47
    л
    0.47
    σουμε
    0.47
    פ
    0.46
    ף
    0.46
    POSITIVE LOGITS
     cytokinin
    0.51
     dėl
    0.50
     cytology
    0.50
     perfek
    0.48
     mengandung
    0.47
     LI
    0.46
     Perfectly
    0.45
     PERFECT
    0.45
     TU
    0.44
     mucosa
    0.44
    Activations Density 0.000%

    No Known Activations